Public repository with the training data from "Mapping Synthetic Observations to Prestellar Core Models: An Interpretable Machine Learning Approach" by T. Grassi et al. (https://arxiv.org/abs/2502.07874).

Content:

• main.ipynb Notebook explaining how to load the data
• X_data.npy Synthetic spectrum for all the 3000 models
• X_data_info.npy List of molecules
• y_data.pkl Models parameter
• y_data_info.pkl Info on model parameters

How to cite

@ARTICLE{2025A&A...702A..71G,
       author = {{Grassi}, T. and {Padovani}, M. and {Galli}, D. and {Vaytet}, N. and {Jensen}, S.~S. and {Redaelli}, E. and {Spezzano}, S. and {Bovino}, S. and {Caselli}, P.},
        title = "{Mapping synthetic observations to pre-stellar core models: An interpretable machine learning approach}",
      journal = {\aap},
     keywords = {astrochemistry, methods: data analysis, methods: numerical, Astrophysics of Galaxies, Instrumentation and Methods for Astrophysics},
         year = 2025,
        month = oct,
       volume = {702},
          eid = {A71},
        pages = {A71},
          doi = {10.1051/0004-6361/202453266},
archivePrefix = {arXiv},
       eprint = {2502.07874},
 primaryClass = {astro-ph.GA},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2025A&A...702A..71G},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}